CN102231791B - Video image defogging method based on image brightness stratification - Google Patents
Video image defogging method based on image brightness stratification Download PDFInfo
- Publication number
- CN102231791B CN102231791B CN 201110182406 CN201110182406A CN102231791B CN 102231791 B CN102231791 B CN 102231791B CN 201110182406 CN201110182406 CN 201110182406 CN 201110182406 A CN201110182406 A CN 201110182406A CN 102231791 B CN102231791 B CN 102231791B
- Authority
- CN
- China
- Prior art keywords
- image
- brightness
- class
- defogging
- defogging method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to a video image defogging method based on image brightness stratification, which is characterized by being based on an Open multiprocessor (MP) technology and being used for processing images in real time by combining an adaptive retinex image defogging method and a defogging method based on dark channel prior-translation. The method comprises the following steps of firstly, stratifying the image brightness by adopting a clustering method to obtain a high brightness image class and a low brightness image class; carrying out blocking partition on each class of images; processing each block in the high brightness image class by using the adaptive retinex image defogging method; processing each block in the low brightness image class by using the defogging method based on dark channel prior-translation; respectively performing an integral normalization process on the gray scale range of a defogging processed result image; and performing Open MP parallelization process on an image fused result and outputting; and therefore, the video image real-time defogging of the image brightness stratification is finished.
Description
Technical field
The present invention relates to video image and handle, particularly a kind of video image defogging method capable based on the image brightness layering.
Background technology
The method that Misty Image is handled mainly is divided into two big classes: figure image intensifying and image restoration.The method of figure image intensifying is a kind of method in common, does not need to consider the formation principle of mist, and this method and other Enhancement Method belong to a class together, mainly is in order to improve the contrast of image, the details of outstanding image.Therefore, this method robust but specially be difficult to the enhancing effect that reaches best at Misty Image comparatively.Another kind method is the model of degenerating according to Misty Image, and simulation is set up corresponding model and carried out inverting, image fault and loss in detail that the compensation degenerative process causes.This method stronger at row, the effect that image is handled also meets people's visual perception.Below mainly analyze the pros and cons of various research methods according to this two main lines.
2, the Misty Image of handling based on image strengthens
Based on the image enchancing method of the overall situation, mainly refer to when the gray scale of image is adjusted the statistical information according to entire image.When less or image scene was simple when mist, this method can obtain certain effect.But scene more complicated in the general scene image, depth information is also more, and general globalize gets processing method can not practical requirement.These class methods mainly contain overall histogram equalization method, homographic filtering method, wavelet filteration method, retinex method, bent wave conversion method, based on the method for atmosphere modulation transfer function.
Topography's Enhancement Method is that relative global image strengthens, the image pixel only correlation with the pixel around it is bigger, estimate conversion or transfer function and results estimated is used for part image to strengthen according to the characteristic of ROI image-region, often can access than the better enhancing effect of global approach.These class methods mainly contain local histogram's equalization methods, local contrast Enhancement Method, based on the Enhancement Method of local variance.
2, restore based on the Misty Image of physical model
Generally to scene depth variation image greatly, after the image recovery, the contrast of partial image region is still lower, generally can not practical requirement.In this case, adopting partial differential equation can be to a certain extent the color definition of image and contrast to be had preferably improves.In addition, scene depth information also is a kind of Useful Information in the Misty Image, information according to scene depth, optical imagery to the greasy weather scene is set up model, image by fine and greasy weather is for referencial use, determine the depth ratio relation of each point in the image, these class methods are applicable to the mist image, then are difficult to satisfy processing requirements for the image of dense fog.A class Physical Modeling is the Misty Image restored method based on prior information in addition.These class methods are main according to being such fact, find that through statistics no mist image must have higher contrast ratio with respect to the image that mist is arranged.Reach the purpose of mist elimination by the local contrast of utilizing the maximization restored image.The general color of image after treatment is too saturated.Afterwards, the researcher had proposed the image mist elimination technology based on the priori of dark primary, and this method is based upon a large amount of image that not influenced by fog of statistics, obtained the statistical law of dark primary.This method is when object brightness is similar to the light of atmosphere, and the dark primary prior information will lose efficacy.
Analysis by above-mentioned pluses and minuses to each class methods as can be known, although these methods exist the difference of essence, each have their own pluses and minuses in the thinking of dealing with problems.
Summary of the invention
The objective of the invention is to, for addressing the above problem, the present invention proposes a kind of video image defogging method capable based on the image brightness layering, and the mist elimination with robustness often needs to merge complementary bigger method, adapts to different scene images.
For achieving the above object, the present invention proposes a kind of video image defogging method capable based on the image brightness layering, it is characterized in that this method is handled image based on Open MP technology in real time with self adaptation retinex image defogging method capable with based on the defogging method capable combination of dark-coloured passage priori; The concrete steps of this method comprise:
Step 1): adopt clustering method to the image brightness layering, obtain high-brghtness picture images class and low-luminosity picture class; And every class image carried out piecemeal;
Step 2): each piece in the high-brghtness picture images class is handled with self adaptation retinex image defogging method capable; Each piece in the low-luminosity picture class used based on the defogging method capable of dark-coloured passage priori handle;
Step 3): to described step 2) figure as a result after mist elimination is handled passes through respectively the whole normalized of tonal range;
Step 4): the result that described step 3) is obtained carries out exporting after Open MP parallelization is handled; So far, finish based on the real-time mist elimination of the video image of image brightness layering.
Described step 2) concrete steps based on the defogging method capable of dark-coloured passage priori in comprise:
Step 21): select brightness value in the shadow channel image to surpass 0.1% pixel of shared image, in these pixels, select the global context light A of the pixel of brightness value maximum
CEstimation;
Step 22): utilize described step 21) the global context light A of the pixel of the brightness value maximum of Huo Deing
CCalculate acquisition transmissivity t (x) according to formula (1);
Wherein, 0<ω≤1; Ω (x) be image block x a localized mass;
Step 23): utilize described step 22) the transmissivity t (x) of Huo Deing handles according to formula (2) mist elimination;
Wherein, I (X)=J (x) t (x)+A (1-t (x)), I (x) is the actual image that receives of greasy weather situation lower sensor, and A (1-t (x)) is surround lighting, and A is global context light, t0=0.1.
The invention has the advantages that proposed a kind of self adaptation retinex algorithm and the video image mist elimination algorithm that combines based on dark primary priori, wherein the retinex algorithm is adaptive retinex algorithm.Divide by the brightness of high-definition image being carried out the zone, be divided into the lower sub-piece of brightness of the higher image subblock of brightness and brightness; Adopt self adaptation retinex algorithm to strengthen at the higher zone of brightness; The lower image of brightness is adopted image defogging method capable based on dark primary priori.Like this can either the advantage of maximized performance retinex algorithm aspect high illumination image mist elimination, can avoid based on the superiority of dark primary priori on low-light (level) the limitation of algorithm when avoiding running into high-brghtness picture images again.
Description of drawings
Fig. 1 is a kind of video image defogging method capable workflow diagram based on the image brightness layering of the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments, technical scheme of the present invention is described in more detail.
HD video mist elimination system is an intelligent graphic image intensifying system. except possessing the performance that real-time processing high-definition image handles, combines with retinex image defogging method capable with based on the defogging method capable (dark mark channel prior) of dark-coloured passage priori. form the image defogging method capable of robust.Whole system mainly comprises the image brightness layering, based on the image mist elimination of retinex with based on mist elimination three parts of dark-coloured passage.
The composition that these three parts are complete the running environment handled of intelligent video image mist elimination, set up perfect operation interface in conjunction with visual studio.The user can be convenient, flexible use, exploitation is safeguarded, oneself the algorithm of specific environment hypograph enhancing of upgrade.
As shown in Figure 1, Fig. 1 is a kind of video image defogging method capable workflow diagram based on the image brightness layering of the present invention.1) image brightness layering
The purpose of image brightness layering is, image is divided into the image level of different brightness, according to the adaptability of algorithm the brightness of algorithm and image coordinated, and expectation reaches optimum mist elimination effect.Change because the retinex algorithm can be suitable for bigger brightness, have higher contrast ratio and strengthen effect, and image brightness is when higher, method based on dark primary priori will lose efficacy, therefore, with image block, the image block of different brightness is adopted diverse ways according to the difference of brightness.Be specially image brightness when higher, adopt the retinex method; When image brightness is low, adopt the method based on dark primary.It is two classes that the image brightness layering adopts the method for cluster that image is gathered, and the image in each class is carried out piecemeal.
2) based on retinex image mist elimination
Retinex image mist elimination algorithm is a kind of algorithm for image enhancement of illumination compensation, its key is the estimation to reflecting component, the whole bag of tricks that proposes is made every effort to strengthen aspects such as effect, inhibition noise, computational efficiency in contrast and is carried out balance, to reach the best visual effect.
3) based on the image defogging method capable of dark-coloured passage priori
3.1 atmospheric scattering model
In computer vision and computer graphics field, the common following expression of the atmospheric scattering model in greasy weather:
I(x)=J(x)t(x)+A(1-t(x))(1-1)
First is direct attenuation components, and second A (1-t (x)) is surround lighting.I (x) is the actual image that receives of greasy weather situation lower sensor, and J (x) is the scene radiancy, and A is global context light, and t (x) is transmissivity, is not finally arrived radiometric ratio of transducer in the expression scene by particle scattering.
When atmosphere supposes that uniformly transmissivity t (x) can be expressed as down:
t(x)=e
-βd(x)(1-2)
Wherein, β represents the scattering coefficient of atmosphere, and d represents the depth of field, and t (x) expression scene radiancy is exponential damping along with the increase of the depth of field.
The mist elimination of Misty Image mainly is exactly from degraded image I (x) restoration scenario radiancy J (x).
3.2 shadow passage (Dark Channel) principle
Shadow passage (Dark Channel) is mainly based on the observation to the outdoor images of fine (haze-free): the most of pixel for non-day dummy section has at least a Color Channel that low-down brightness value is arranged.Change a kind of saying, the minimum luminance value that is exactly these pixels is very low.For piece image J, we define:
J wherein
CBe the Color Channel of image J, be positioned at the localized mass of x centered by the Ω (x).Experiment showed, for most of haze-free outdoor images, at non-day dummy section J
DarkIntensity level very little, even level off to 0.Therefore define shadow passage (Dark Channel) J of image J
Dark
Under the greasy weather situation, because the existence of additional surround lighting, the image brightness height of the shadow passage of image (Dark Channel) when fine.The brightness of the regional shadow passage that mist is more dense is more high.Therefore, the thickness of mist can be similar to by the brightness value of shadow passage.
3.3 the mist elimination process based on Dark channel
3.3.1, estimate global context light
The thickness of the estimation mist that the shadow passage of an image can be used for being similar to.Therefore, can estimate global context light by the shadow passage.At first selecting brightness value in the shadow channel image is preceding 0.1% pixel, and these pixels are represented the light tight zone that mist is the thickest, in these pixels, select the pixel of brightness value maximum in input picture I as the estimation of global context light then.
3.3.2, estimate projection ratio
Suppose that transmissivity is constant in a little regional area Ω (x).Transmissivity in the definition Ω (x) is t (x).For Misty Image, in regional area, formula (1-1) is minimized, obtain:
Notice respectively each Color Channel is asked minimum computing, following formula can be equivalent to:
Three passages are asked minimum, obtain:
According to the principle of shadow passage (Dark Channel), the shadow passage J of the radiancy J of fine (haze-free) image
DarkValue level off to 0, and global context light A
CBe generally on the occasion of, therefore can obtain
With following formula substitution formula (1-6), can obtain the estimation expression formula of transmissivity:
For the sky dummy section, because the color of day dummy section is approximately equal to global context light A under the situation in greasy weather, so regional on high:
Transmissivity levels off to 0.When therefore handling, do not need to be partitioned into separately in advance a day dummy section.
In the reality, even under the situation of fine day, still have very small particles in the air, so still there are a spot of mist in people when seeing distant objects, and the existence of mist more is conducive to the depth information that people go the perception scene.Therefore in the process of mist elimination, should selectively keep the information of a small amount of mist, can realize by introducing a constant parameter ω (0<ω≤1) here:
The value of parameter ω can be chosen according to practical application.
3.3.3, mist elimination
After estimating the transmissivity image, (1-1) recovers degraded image according to formula.Under transmissivity t (x) leveled off to 0 situation, directly attenuation components J (x) t (x) also leveled off to 0, and the image J after so direct recovery is likely noise.Therefore, limit transmissivity smallest limit t0 (general t0=0.1) here, show that keeping a spot of mist in the thick fog zone exists.Image J (x) after replying at last is:
The real-time mist elimination of intelligence high clear video image system innovates on the method basis of traditional images mist elimination and improves.Having proposed high-definition image first from system aspects strengthens mist elimination and has built a basic real-time enhancing system.Aspect algorithm, by with image block, adopt self adaptation retinex algorithm and image block based on the different brightness layers of dark primary priori algorithm process respectively.Both take full advantage of the advantage of two kinds of algorithms, jumped out the limitation of dark primary elder generation checking method again.Aspect acceleration realization high clear video image mist elimination, adopt Open MP concurrent technique that algorithm is accelerated to handle.
Innovative point of the present invention comprises:
1, theory innovation
Proposed a kind of retinex algorithm and the video image mist elimination algorithm that combines based on dark primary priori, wherein the retinex algorithm is adaptive retinex algorithm.Divide by the brightness of high-definition image being carried out the zone, be divided into the lower sub-piece of brightness of the higher image subblock of brightness and brightness; Adopt self adaptation retinex algorithm to strengthen at the higher zone of brightness; The lower image of brightness is adopted image defogging method capable based on dark primary priori.Like this can either the advantage of maximized performance retinex algorithm aspect high illumination image mist elimination, can avoid based on the superiority of dark primary priori on low-light (level) the limitation of algorithm when avoiding running into high-brghtness picture images again.Traditional method is that image is carried out whole processing is irrational, and particularly for high-definition image, the detailed information of image local, the deep or light situation of mist etc. are uneven, therefore also just cannot treat different things as the same, and need divide and rule.
2, application innovation
Propose first and realized the real-time mist elimination of 5,000,000 high clear video images and be applied in the supervisory control system.A realtime graphic mist elimination system is particularly based on the mist elimination system of high clear video image, and its googol all is strict to the performance demands that strengthens algorithm performance and system according to amount.The enhancing system realizes at the platform of visual studio, has also adopted the design of hommization in the design of man-machine interaction.
At present, the image mist elimination system on market is based on all that the SD video carries out.Along with development of science and technology and demands of applications, the SD image more and more can not be satisfied the demand.The alternative SD image of high clear video image is an inevitable trend in laying and monitoring.The camera of present high definition is more and more, and the HD video of acquisition is also more and more.But also there is a huge wide gap between huge demand and the high clear video image enhancing system in real time.Therefore, the appearance of the real-time mist elimination of intelligent HD video system will remedy this vacancy.
3, technological innovation
Technological innovation one:
Picture portion territory self adaptation mist elimination algorithm mainly is the method for carrying out the image mist elimination at different image-regions targetedly.This algorithm is through strict right demonstration and lot of experiment validation, mist elimination at high clear video image under the complex environment can adopt the picture portion territory fully, adopts self adaptation retinex mist elimination targetedly and combines based on the image mist elimination algorithm of dark primary priori and carry out the image mist elimination.
Technological innovation two:
The parallel processing of data and algorithm is carried out in employing to high-definition image based on the parallelization treatment technology of Open MP.The algorithm aspect can realize the multithreading processing on the one hand.Open MP is a kind of multi-threaded parallel treatment technology, is widely used in the large-scale data computing, at present in image processing field rare relating to also.In the high clear video image extensive use, can bring into play its huge parallel processing capability.By the design of multithreading, can make the operation of the high property of computer.The parallel processing of data aspect on the other hand.View data can be regarded a big matrix as, so its data have good concurrency, is fit to very much carry out parallel processing
It should be noted last that above embodiment is only unrestricted in order to technical scheme of the present invention to be described.Although the present invention has been described in detail with reference to embodiment, those of ordinary skill in the art is to be understood that, technical scheme of the present invention is made amendment or is equal to replacement, do not break away from design and the scope of technical solution of the present invention, it all should be encompassed in the middle of the claim scope of the present invention.
Claims (1)
1. the video image defogging method capable based on the image brightness layering is characterized in that, this method is handled image based on Open MP technology in real time with self adaptation retinex image defogging method capable with based on the defogging method capable combination of dark-coloured passage priori; The concrete steps of this method comprise:
Step 1): adopt clustering method to the image brightness layering, obtain high-brghtness picture images class and low-luminosity picture class; And every class image carried out piecemeal;
Step 2): each piece in the high-brghtness picture images class is handled with self adaptation retinex image defogging method capable; Each piece in the low-luminosity picture class used based on the defogging method capable of dark-coloured passage priori handle;
Step 3): to described step 2) figure as a result after mist elimination is handled passes through respectively the whole normalized of tonal range;
Step 4): the result that described step 3) is obtained carries out exporting after Open MP parallelization is handled; So far, finish based on the real-time mist elimination of the video image of image brightness layering.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110182406 CN102231791B (en) | 2011-06-30 | 2011-06-30 | Video image defogging method based on image brightness stratification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110182406 CN102231791B (en) | 2011-06-30 | 2011-06-30 | Video image defogging method based on image brightness stratification |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102231791A CN102231791A (en) | 2011-11-02 |
CN102231791B true CN102231791B (en) | 2013-08-14 |
Family
ID=44844320
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 201110182406 Expired - Fee Related CN102231791B (en) | 2011-06-30 | 2011-06-30 | Video image defogging method based on image brightness stratification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102231791B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104715559A (en) * | 2015-03-06 | 2015-06-17 | 温州大学 | Smoke detection and fire alarm method based on trajectory identification |
CN107545544A (en) * | 2016-06-29 | 2018-01-05 | 诺基亚技术有限公司 | The method and apparatus for removing the turbid object in image |
Families Citing this family (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103164845B (en) * | 2011-12-16 | 2016-08-03 | 中国科学院沈阳自动化研究所 | A kind of real-time image mist elimination device and method |
CN103186887B (en) * | 2011-12-30 | 2016-08-03 | 株式会社日立制作所 | Image demister and image haze removal method |
CN102609704A (en) * | 2012-03-23 | 2012-07-25 | 上海海事大学 | Detecting device and method of video monitoring image movement targets under foggy weather conditions |
CN103049888A (en) * | 2012-12-07 | 2013-04-17 | 西安电子科技大学 | Image/video demisting method based on combination of dark primary color of atmospheric scattered light |
CN103218778B (en) * | 2013-03-22 | 2015-12-02 | 华为技术有限公司 | The disposal route of a kind of image and video and device |
CN103793899B (en) * | 2014-01-23 | 2017-04-12 | 武汉大学 | True color image fusion method based on multi-phase wavelet transformation and MTFC |
CN103914820B (en) * | 2014-03-31 | 2017-01-18 | 华中科技大学 | Image haze removal method and system based on image layer enhancement |
CN104717400A (en) * | 2015-02-03 | 2015-06-17 | 北京理工大学深圳研究院 | Real-time defogging method of monitoring video |
CN105096272B (en) * | 2015-08-19 | 2018-02-02 | 常州工学院 | A kind of defogging method based on dual-tree complex wavelet |
CN106504205A (en) * | 2016-10-20 | 2017-03-15 | 凌云光技术集团有限责任公司 | A kind of image defogging method and terminal |
CN107194900A (en) * | 2017-07-27 | 2017-09-22 | 广东欧珀移动通信有限公司 | Image processing method, device, computer-readable recording medium and mobile terminal |
CN107451977B (en) * | 2017-08-07 | 2020-08-21 | 河南工业大学 | Image defogging method and system |
CN110175963B (en) * | 2019-05-28 | 2021-02-09 | 山东大学 | Dual-purpose image enhancement method and device suitable for underwater image and atmospheric dark image |
CN110852971B (en) * | 2019-11-11 | 2022-02-18 | 昆明理工大学 | Video defogging method based on dark channel prior and Retinex and storage medium |
CN111627223A (en) * | 2020-05-12 | 2020-09-04 | 浙江工贸职业技术学院 | Highway traffic accident detection and early warning system and method |
CN112116807B (en) * | 2020-08-31 | 2021-11-30 | 广西交科集团有限公司 | Multifunctional traffic safety guiding device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101754032A (en) * | 2008-12-12 | 2010-06-23 | 汉王科技股份有限公司 | Defogging method capable of keeping colors |
CN101783012A (en) * | 2010-04-06 | 2010-07-21 | 中南大学 | Automatic image defogging method based on dark primary colour |
CN102044070A (en) * | 2011-01-10 | 2011-05-04 | 北京师范大学 | Retinex based nonlinear color image enhancement method |
CN102063706A (en) * | 2010-12-23 | 2011-05-18 | 哈尔滨工业大学(威海) | Rapid defogging method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8111943B2 (en) * | 2009-04-15 | 2012-02-07 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Smart image enhancement process |
-
2011
- 2011-06-30 CN CN 201110182406 patent/CN102231791B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101754032A (en) * | 2008-12-12 | 2010-06-23 | 汉王科技股份有限公司 | Defogging method capable of keeping colors |
CN101783012A (en) * | 2010-04-06 | 2010-07-21 | 中南大学 | Automatic image defogging method based on dark primary colour |
CN102063706A (en) * | 2010-12-23 | 2011-05-18 | 哈尔滨工业大学(威海) | Rapid defogging method |
CN102044070A (en) * | 2011-01-10 | 2011-05-04 | 北京师范大学 | Retinex based nonlinear color image enhancement method |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104715559A (en) * | 2015-03-06 | 2015-06-17 | 温州大学 | Smoke detection and fire alarm method based on trajectory identification |
CN107545544A (en) * | 2016-06-29 | 2018-01-05 | 诺基亚技术有限公司 | The method and apparatus for removing the turbid object in image |
Also Published As
Publication number | Publication date |
---|---|
CN102231791A (en) | 2011-11-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102231791B (en) | Video image defogging method based on image brightness stratification | |
CN102750674B (en) | Video image defogging method based on self-adapting allowance | |
Tripathi et al. | Single image fog removal using anisotropic diffusion | |
CN108734670B (en) | Method for restoring single night weak-illumination haze image | |
CN103258332B (en) | A kind of detection method of the moving target of resisting illumination variation | |
CN103501401B (en) | Towards super large noise real-time video based on pre-filtering denoising method | |
CN106530240B (en) | A kind of image defogging method optimized based on Multiscale Fusion and full variation | |
Molnár et al. | Illumination-robust variational optical flow using cross-correlation | |
CN102831591A (en) | Gaussian filter-based real-time defogging method for single image | |
CN103218778A (en) | Image and video processing method and device | |
CN104867121B (en) | Image Quick demisting method based on dark primary priori and Retinex theories | |
Wang et al. | Variational single nighttime image haze removal with a gray haze-line prior | |
CN104200445A (en) | Image defogging method with optimal contrast ratio and minimal information loss | |
CN103020914A (en) | Rapid image defogging method based on spatial continuity principle | |
CN103345733A (en) | Rapid low-illumination image enhancing method based on improved dark channel prior | |
CN107818547A (en) | The minimizing technology of the spiced salt and Gaussian mixed noise in a kind of sequence towards twilight image | |
CN105931208A (en) | Physical model-based low-illuminance image enhancement algorithm | |
CN105096272A (en) | De-hazing method based on dual-tree complex wavelet | |
CN102646267B (en) | Degraded image restoration method and system | |
CN106657948A (en) | low illumination level Bayer image enhancing method and enhancing device | |
Huang et al. | Improved algorithm for image haze removal based on dark channel priority | |
Singh et al. | Weighted least squares based detail enhanced exposure fusion | |
CN102789634B (en) | A kind of method obtaining illumination homogenization image | |
CN107481211B (en) | Night traffic monitoring enhancement method based on gradient domain fusion | |
Mao et al. | Clarity method of fog and dust image in fully mechanized mining face |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130814 Termination date: 20150630 |
|
EXPY | Termination of patent right or utility model |